© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 97861
    Prev
    Next
    INDEX
    Explanations

    weaver

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_14_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     αυτή
    0.59
     nascost
    0.54
     ELECT
    0.54
     пишу
    0.54
     Srps
    0.53
     elettronica
    0.53
     Echt
    0.51
    బ
    0.51
     ज्वाला
    0.51
     स्पून
    0.51
    POSITIVE LOGITS
    FormParams
    0.52
     రైతు
    0.50
    istle
    0.49
    .³
    0.49
     ministers
    0.47
     मांगों
    0.47
    থাক
    0.46
     평
    0.46
    ğmen
    0.46
     shippers
    0.46
    Activations Density 0.001%

    No Known Activations